© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10033
    Prev
    Next
    INDEX
    Explanations

    terms associated with equilibrium states in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    awtextra
    -0.77
     виправивши
    -0.75
     wave
    -0.73
     WAVE
    -0.72
     Wave
    -0.68
    Flyer
    -0.68
    ability
    -0.65
     $('<
    -0.63
     Spazier
    -0.63
    GeneratedCode
    -0.63
    POSITIVE LOGITS
    quilibrium
    1.48
     Equilibrium
    1.27
    Equilibrium
    1.21
    equilibrium
    1.20
     equilibrium
    1.19
    ilibrium
    1.17
     equilibria
    0.96
    Controllo
    0.81
    SBATCH
    0.75
    AsyncResult
    0.72
    Activations Density 0.004%

    No Known Activations